v4l3n71n/web_scrap
1
0
Fork 0
Code Issues Pull Requests Projects Releases 10 Wiki Activity

getting post title

Browse Source
This commit is contained in:
Valentin CZERYBA 2023-07-15 11:51:15 +02:00
parent 5fe4b1f786
commit 7593b68b6c
1 changed files with 28 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
lib/WPMenu.py
View File

@ -74,10 +74,38 @@ class WPMenu:
except Exception as err:
self._logger.error("{0} : Exception error for get url {1} : {2}".format(self._name, canalblog, err))
def _getIdfromTitlePost(self, content):
idMenu = 0
return idMenu
def _getIdFromPost(self, href):
idMenu = 0
o = urlparse(href)
if len(o.netloc) > 0:
try:
page = self._request_canalblog.get(href)
if page.status_code == 200:
self._logger.info("{0} : Get content : {1}".format(self._name, href))
self._getIdfromTitlePost(page.content)
else:
self._logger.error("{0} : {2} didn't get due status code : {1}".format(self._name, page.status_code, i))
self._logger.debug("{0} : {1}".format(self._name, page.content))
except ConnectionError as err:
self._logger.error("{0} : Connection error for get url {1} : {2}".format(self._name, href, err))
exit(1)
except Exception as err:
self._logger.error("{0} : Exception error for get url {1} : {2}".format(self._name, href, err))
else:
if os.path.exists("{0}/..{1}".format(self._directory, o.path)):
try:
content = open("{0}/..{1}".format(self._directory, o.path), "r")
self._getIdfromTitlePost(content)
except Exception as err:
self._logger.error("{0} : Exception error for get file content {1} : {2}".format(self._name, href, err))
return idMenu
def _getIdFromReverse(self, title, href):
self._logger.info("{0} : get title {1} from href {2}".format(self._name, title, href))
idMenu = 0